Dual-Band Scene Classification Based on Convolutional Features and Bayesian Decision

Xiaohua Qiu; Min Li; Liqiong Zhang; Lin Dong

doi:10.3788/LOP202158.0415006

Laser & Optoelectronics Progress, Volume. 58, Issue 4, 0415006(2021)

Dual-Band Scene Classification Based on Convolutional Features and Bayesian Decision

Xiaohua Qiu^1,2、*, Min Li^1、*, Liqiong Zhang¹, and Lin Dong²

Author Affiliations

¹College of Operational Support, The Rocket Force University of Engineering, Xi'an, Shaanxi 710025, China

²College of Information Engineering, Engineering University of PAP, Xi'an, Shaanxi 710086, China

show less

Abstract Get PDF(in Chinese)

Figures & Tables(10)

Fig. 1. Framework diagram of our method

Download full size

Fig. 2. Example image of the RGB-NIR dataset

Download full size

Fig. 3. Classification accuracies of the two features. (a) RGB image; (b) NIR image; (c) RGB-NIR image

Download full size

Fig. 4. Influence of the different threshold value on model classification accuracy. (a) C5 layer; (b) F6 layer; (c) F7 layer

Download full size

Fig. 5. Classification accuracies of different CNN models. (a) VGG-16 model; (b) VGG-19 model; (c) ResNet-50 model

Download full size

Fig. 6. Classification accuracy confusion matrix of our method. (a) Best classification accuracy in the 20 groups (98.0%); (b) worst classification accuracy in the 20 groups (88.9%)

Download full size

Table 1. Layers and feature dimension of the VGGNet and ResNet
View table
Table 1. Layers and feature dimension of the VGGNet and ResNet
Hierarchical feature Low level Middle level High level
C2 C3 C4 C5 F6(G6) F7
VGGNet 56×56×128 28×28×256 14×14×512 7×7×512 4096 4096
ResNet-50 56×56×256 28×28×512 14×14×1024 7×7×2048 2048 --

Table 2. Dimensions of different features of the VGG-16 model
View table
Table 2. Dimensions of different features of the VGG-16 model
Layer C2 C3 C4 C5 F6 F7
CNN feature 401408 200704 100352 25088 4096 4096
PCA feature of RGB 359 360 361 344 328 312
PCA feature of NIR 361 362 361 350 338 322

Table 3. Classification accuracies of different CNN models at different t unit: %

View table

Table 3. Classification accuracies of different CNN models at different t unit: %

Model	C5			F6(G6)			F7
Model	0.90	0.95	0.99	0.90	0.95	0.99	0.90	0.95	0.99
VGG-16	90.6±2.5	90.3±2.4	90.5±2.4	91.9±2.3	92.0±2.5	91.9±2.1	92.4±2.7	93.3±2.0	92.9±2.5
VGG-19	90.1±2.3	89.8±2.3	89.9±2.3	91.1±2.6	91.3±2.5	92.0±2.5	91.5±3.3	91.3±3.4	90.7±3.0
ResNet-50	91.8±1.9	92.1±2.1	92.2±2.0	94.0±2.1	94.0±2.2	94.3±2.1	--	--	--

Table 4. Classification accuracy comparison of different methods

View table

Table 4. Classification accuracy comparison of different methods

Method	Train/testgroup	Year	Classification accuracy /%
Method	Train/testgroup	Year	RGB	NIR	RGB+NIR
MSIFT	10	2011	62.9±3.1	--	73.1±3.3
Fisher Vector	10	2011	84.5±2.3	--	87.9±2.2
mCENTRIST	10	2014	78.9±5.1	--	84.5±2.1
DSIFT_CLM	1	2018	--	--	86.9
Dual CNN (GoogLeNet)	1	2017	--	--	92.5
CNN_KPCA_CCA (GoogLeNet)	1	2018	--	--	90.8
MCNN (ResNet-50)	1	2019	--	--	93.5
DC_CNN	1	2019	--	--	95.0
Our method (worst)	1(20)	2020	87.9	80.8	88.9
Our method (best)	1(20)	2020	96.0	93.9	98.0
Our method (ResNet-50)	20	2020	92.3±1.9	88.7±3.2	94.3±2.1

Tools

Get Citation

Copy Citation Text

Xiaohua Qiu, Min Li, Liqiong Zhang, Lin Dong. Dual-Band Scene Classification Based on Convolutional Features and Bayesian Decision[J]. Laser & Optoelectronics Progress, 2021, 58(4): 0415006

Download Citation

EndNote(RIS)BibTex Plain Text

Set citation alerts for article

Save article for my favorites